Zebra: In-Context Generative Pretraining for Solving Parametric PDEs Solving time-dependent parametric partial differential equations (PDEs) is challenging for data-driven methods, as these models must adapt to variations in parameters such as coefficients, forcing ter...

Leveraging LLMs' in-context learning for modeling physical dynamics. Paper #ICML2025.
"Zebra: In-Context Generative Pretraining for Solving Parametric PDEs", Louis Serrano, Armand Kassai, Thomas Wang, Pierre ERBACHER, Patrick Gallinari
📄 arxiv.org/abs/2410.03437
🖥️ github.com/LouisSerrano...

We're recruiting a PhD student in machine learning at Sorbonne University (Paris) for Fall 2025!

Topic: AI4Science & Generative Models

Title: Deep Generative Models of Physical Dynamics

🔗 pages.isir.upmc.fr/gallinari/op...

#PhDPosition #AI4Science #DeepLearning #PhysicsML

#ICLR2025 recap' 🇸🇬
Great time at ICLR2025 for our team, who presented their work during the poster sessions!
➡️ SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation iclr.cc/virtual/2025...

ML4CFD Competition #neurips2024
neurips.cc/virtual/2024...

Two papers #NeurIPS2024 from my group on physics-aware ML
AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields
openreview.net/pdf?id=Aj8RK...

Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
openreview.net/pdf?id=GuY0z...